Related papers: EVE: A Generator-Verifier System for Generative Po…

Reinforcement learning (RL) for LLM post-training faces a fundamental design choice: whether to use a learned critic as a baseline for policy optimization. Classical theory favors critic-based methods such as PPO for variance reduction, yet…

Pre-trained multi-modal vision-language models (VLMs) are becoming increasingly popular due to their exceptional performance on downstream vision applications, particularly in the few- and zero-shot settings. However, selecting the…

Recent advancements in Vision-Language Models (VLMs) have demonstrated strong capabilities in general visual reasoning, yet their applicability to rigorous biometric tasks remains unexplored. This work presents an exploratory study…

In the context of multi-agent systems, the rational verification problem is concerned with checking which temporal logic properties will hold in a system when its constituent agents are assumed to behave rationally and strategically in…

Adapting large language models (LLMs) to a targeted task efficiently and effectively remains a fundamental challenge. Such adaptation often requires iteratively improving the model toward a targeted task, yet collecting high-quality…

We present a data-efficient framework for solving visuomotor sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models. Our framework trains deep visuomotor…

Recent work in synthetic data generation in the time-series domain has focused on the use of Generative Adversarial Networks. We propose a novel architecture for synthetically generating time-series data with the use of Variational…

Vision-language models (VLMs) are impactful in part because they can be applied to a variety of visual understanding tasks in a zero-shot fashion, without any fine-tuning. We study $\textit{generative VLMs}$ that are trained for next-word…

Large language models (LLMs) make reward design in reinforcement learning substantially more scalable, but generated rewards are not automatically reliable training objectives. Existing work has focused primarily on generating, evolving, or…

Reinforcement Learning (RL) has significantly advanced Large Language Models (LLMs) in verifiable domains, but aligning models for open-ended generation remains profoundly challenging due to the lack of definitive rewards. Current…

Large Language Models (LLMs) have demonstrated great potential in automating the generation of Verilog hardware description language code for hardware design. This automation is critical to reducing human effort in the complex and…

Autonomous LLM-based agents are increasingly engaging in decentralized service interactions to collaboratively execute complex tasks. However, the intrinsic instability and low-cost generativity of LLMs introduce a systemic vulnerability,…

LLM-based agents depend on effective tool-use policies to solve complex tasks, yet optimizing these policies remains challenging due to delayed supervision and the difficulty of credit assignment in long-horizon trajectories. Existing…

Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation. One key factor is the exploitation of smooth latent structures to guide the generation. However, the…

The integration of Vision-Language Models (VLMs) into autonomous driving systems has shown promise in addressing key challenges such as learning complexity, interpretability, and common-sense reasoning. However, existing approaches often…

The advent of foundation models, which are pre-trained on vast datasets, has ushered in a new era of computer vision, characterized by their robustness and remarkable zero-shot generalization capabilities. Mirroring the transformative…

In autonomous driving, dynamic environment and corner cases pose significant challenges to the robustness of ego vehicle's state understanding and decision making. We introduce VDRive, a novel pipeline for end-to-end autonomous driving that…

The safe deployment of autonomous driving systems (ADSs) relies on comprehensive testing and evaluation. However, safety-critical scenarios that can effectively expose system vulnerabilities are extremely sparse in the real world. Existing…

Vision-Language-Action (VLA) models are emerging as highly effective planning models for end-to-end autonomous driving systems. However, current works mostly rely on imitation learning from sparse trajectory annotations and under-utilize…

Generative engines (GEs) are reshaping information access by replacing ranked links with citation-grounded answers, yet current Generative Engine Optimization (GEO) methods optimize each instance in isolation, unable to accumulate or…